jfforero/distilbert-base-uncased-BERT-POET4

This model is a fine-tuned version of distilbert-base-uncased for sentiment analysis.

Model description

This model is trained for sentiment classification with three labels: positive, neutral, and negative. It is based on DistilBERT, a lighter and faster version of BERT.

Intended uses & limitations

Intended Use

• Sentiment classification of short texts, such as product reviews or social media posts.
• Designed for English-language input.

Limitations

• May struggle with sarcasm or complex irony.
• Performance depends on training data quality.

Training and evaluation data

• Fine-tuned on [Dataset Name] (if available, add link).
• Contains X training samples and Y validation samples.

Training procedure

Training hyperparameters

• Optimizer: AdamW
• Learning Rate: 2e-5
• Batch Size: X
• Epochs: Y

Training results

Train Loss	Validation Loss	Epoch
X.XXXX	Y.YYYY	Z

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Datasets 2.19.0
• Tokenizers 0.15.2